还原record.py代码

core/recorder.py

@@ -16,11 +16,8 @@ import tempfile
 import wave
 from core import fay_core
 from core import interact
-
-import re
-
 # 启动时间 (秒)
-_ATTACK = 0.05 # 更快进入拾音，减少短唤醒词被漏掉的概率
+_ATTACK = 0.2
 
 # 释放时间 (秒)
 _RELEASE = 0.7
@@ -88,31 +85,6 @@ class Recorder:
         with fay_core.auto_play_lock:
             fay_core.can_auto_play = True
 
-    def _norm_asr_text(self, s: str) -> str:
-        """
-        大厅场景：ASR 结果常见问题
-        - 句首有空格/标点/语气词（嗯、啊、这个...）
-        - 唤醒词后跟逗号、冒号等
-        所以需要做最小必要的规范化，避免 front 模式误判为“待唤醒”
-        """
-        if not s:
-            return ""
-        s = s.strip()
-        # 去掉句首标点/空白
-        s = re.sub(r'^[\s，,。.!！？:：、~～]+', '', s)
-        # 去掉句首常见语气词（按需可继续加）
-        s = re.sub(r'^(嗯|啊|呃|额|哦|唔|这个|那个)\s*', '', s)
-        return s
-
-    def _strip_wake_prefix(self, full_text: str, wake_word: str) -> str:
-        """
-        去除前置唤醒词，只把“真正的问题”交给对话系统
-        例如：'小F，播放音乐' -> '播放音乐'
-        """
-        rest = full_text[len(wake_word):]
-        # 吞掉唤醒词后的空白/标点
-        return rest.lstrip(" \t，,。.!！？:：、~～")
-
     def __waitingResult(self, iat: asrclient, audio_data):
         self.processing = True
         t = time.time()
@@ -169,83 +141,34 @@ class Recorder:
                         self.timer.cancel()  # 取消之前的计时器任务
                         self.timer = threading.Timer(60, self.reset_wakeup_status)  # 重设计时器为60秒
                         self.timer.start()
-
+                
-                # 前置唤醒词模式（大厅优化版）
+                #前置唤醒词模式
-                elif cfg.config['source']['wake_word_type'] == 'front':
+                elif  cfg.config['source']['wake_word_type'] == 'front':
-                    wake_word = cfg.config['source']['wake_word']
+                    wake_word =  cfg.config['source']['wake_word']
-                    wake_word_list = [w.strip() for w in wake_word.split(',') if w.strip()]
+                    wake_word_list = wake_word.split(',')
-
-                    raw_text = text
-                    text2 = self._norm_asr_text(raw_text)
-
                     wake_up = False
-                    matched_word = None
+                    for word in wake_word_list:
-
+                        if text.startswith(word):
-                    # 1) 规范化后做“严格句首匹配”
+                            wake_up_word = word
-                    for w in wake_word_list:
-                        w2 = self._norm_asr_text(w)
-                        if w2 and text2.startswith(w2):
                             wake_up = True
-                            matched_word = w2
                             break
-
-                    # 2) 容错：允许唤醒词出现在句首很短范围内（防止语气词未完全清掉）
-                    #    注意：范围要小，避免大厅误唤醒
-                    if not wake_up:
-                        N = 4  # 建议 3~6，越大越容易误触发
-                        head = text2[:N]
-                        for w in wake_word_list:
-                            w2 = self._norm_asr_text(w)
-                            if w2 and w2 in head:
-                                wake_up = True
-                                matched_word = w2
-                                # 从唤醒词出现的位置截断，确保 strip 正确
-                                idx = text2.find(w2)
-                                text2 = text2[idx:]
-                                break
-
                     if wake_up:
-                        util.printInfo(1, self.username, f"唤醒成功！(front:{matched_word})")
+                        util.printInfo(1, self.username, "唤醒成功！")
                         if wsa_server.get_web_instance().is_connected(self.username):
-                            wsa_server.get_web_instance().add_cmd({
+                            wsa_server.get_web_instance().add_cmd({"panelMsg": "唤醒成功！", "Username" : self.username , 'robot': f'http://{cfg.fay_url}:5000/robot/Listening.jpg'})
-                                "panelMsg": "唤醒成功！",
-                                "Username": self.username,
-                                'robot': f'http://{cfg.fay_url}:5000/robot/Listening.jpg'
-                            })
                         if wsa_server.get_instance().is_connected(self.username):
-                            content = {
+                            content = {'Topic': 'Unreal', 'Data': {'Key': 'log', 'Value': "唤醒成功！"}, 'Username' : self.username, 'robot': f'http://{cfg.fay_url}:5000/robot/Listening.jpg'}
-                                'Topic': 'Unreal',
-                                'Data': {'Key': 'log', 'Value': "唤醒成功！"},
-                                'Username': self.username,
-                                'robot': f'http://{cfg.fay_url}:5000/robot/Listening.jpg'
-                            }
                             wsa_server.get_instance().add_cmd(content)
-
+                        #去除唤醒词后语句
-                        # ✅ 关键：剥离唤醒词，把真正问题交给对话系统
+                        question = text#[len(wake_up_word):].lstrip()
-                        question = self._strip_wake_prefix(text2, matched_word)
-
-                        # 如果只说了唤醒词（或后面太短），给一句提示
-                        if not question:
-                            question = "在呢，你说？"
-
                         self.on_speaking(question)
                         self.processing = False
                     else:
-                        # ✅ 关键：打印原始识别和规范化后文本，现场好定位为何没匹配上
+                        util.printInfo(1, self.username, "[!] 待唤醒！")
-                        util.printInfo(1, self.username, f"[!] 待唤醒！(front) ASR='{raw_text}' norm='{text2}'")
                         if wsa_server.get_web_instance().is_connected(self.username):
-                            wsa_server.get_web_instance().add_cmd({
+                            wsa_server.get_web_instance().add_cmd({"panelMsg": "[!] 待唤醒！", "Username" : self.username , 'robot': f'http://{cfg.fay_url}:5000/robot/Normal.jpg'})
-                                "panelMsg": "[!] 待唤醒！",
-                                "Username": self.username,
-                                'robot': f'http://{cfg.fay_url}:5000/robot/Normal.jpg'
-                            })
                         if wsa_server.get_instance().is_connected(self.username):
-                            content = {
+                            content = {'Topic': 'Unreal', 'Data': {'Key': 'log', 'Value': "[!] 待唤醒！"}, 'Username' : self.username, 'robot': f'http://{cfg.fay_url}:5000/robot/Normal.jpg'}
-                                'Topic': 'Unreal',
-                                'Data': {'Key': 'log', 'Value': "[!] 待唤醒！"},
-                                'Username': self.username,
-                                'robot': f'http://{cfg.fay_url}:5000/robot/Normal.jpg'
-                            }
                             wsa_server.get_instance().add_cmd(content)
 
             #非唤醒模式
@@ -311,10 +234,7 @@ class Recorder:
 
             #计算音量是否满足激活拾音
             level = audioop.rms(data, 2)
-
+            if len(self.__history_data) >= 10:#保存激活前的音频，以免信息掉失
-            # 把激活前缓存拉长，避免“唤醒词”在触发拾音前被漏掉
-            # 1024帧@16kHz≈64ms/块，30块≈1.9秒
-            if len(self.__history_data) >= 30:  # 保存激活前的音频，以免信息掉失
                 self.__history_data.pop(0)
             if len(self.__history_level) >= 500:
                 self.__history_level.pop(0)